[{"data":1,"prerenderedAt":776},["ShallowReactive",2],{"method-rusu2009fpfh":3},{"method":4,"reference":41,"equipment":61,"figures":62,"results":63},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":21,"limitations":26,"sensors":28,"platform":29,"estimator":30,"association":31,"timeModel":32,"deskew":32,"loopClosure":33,"globalOptimization":33,"mapRepresentation":34,"prior":35,"outputGeometry":36,"compute":37,"codeUrl":38,"codeLicense":39,"relatedVersions":40},"rusu2009fpfh","Rusu et al., 2009","FPFH \u002F SAC-IA","Fast Point Feature Histograms (FPFH) for 3D registration",2009,"classic","C02","registration_component","作者先整理點特徵直方圖（PFH）：在查詢點半徑內的鄰點兩兩建立 Darboux 座標框，統計三個角度特徵，並刪去原本的距離特徵；再以快取與點重新排序縮短實際計算時間。快速點特徵直方圖（FPFH）只計算每點與其鄰點的簡化直方圖（SPFH），再依距離加權鄰點的 SPFH，使複雜度由 O(n·k²) 降為 O(n·k)，並把三個特徵拆成獨立直方圖串接。SAC-IA 從特徵相似的候選點隨機抽取對應來求剛體轉換，以 Huber 懲罰評分，最後用 Levenberg-Marquardt 細化。在一組重疊約 45% 的 Ljubljana 都市戶外資料上，SAC-IA 以 1000 次迭代、10462 點在 34 秒內完成，先前的貪婪初始對齊只用 200 點就超過 17 分鐘（Table I）。論文沒有提供配準精度的量化數據，驗證場景僅 Stanford bunny 與這組戶外資料。","FPFH is a faster reformulation of PFH local descriptors; SAC-IA uses them for sample-consensus initial alignment before local refinement.","full_text_reviewed","peer_reviewed_published","main_body","not_reported（僅以 Stanford bunny 與一組 Ljubljana 都市戶外重疊點雲測試，未涉及營建場域）",[20],"public_benchmark",[22,23,24,25],"drastically reduced computation, O(n k) instead of O(n k^2), while retaining most PFH discriminative power (Sec. III-A, III-B)","FPFH signatures still separate plane, cylinder, sphere, edge and corner points (Sec. III-C, Fig. 7)","incremental online computation for single-sweep scans (Sec. III-D, Alg. 1)","SAC-IA 34 s vs > 17 min and > 43 min for greedy alignment while using over 10000 points (Table I)",[27],"FPFH loses some fine detail compared with PFH (bunny face and front leg) and its primitive signatures are less informative (Sec. III-B, III-C); the online algorithm applies only to single-sweep scans and adds a small delay (Sec. III-D); evaluation limited to Stanford bunny scans and one Ljubljana urban outdoor pair, with registration results shown only as figures and no quantitative accuracy metric (Sec. II to V; reviewer observation); robustness on noisier stereo or time-of-flight data left to future work (Sec. VI); handcrafted descriptor correspondences can contain very high outlier ratios at large viewpoint changes (lim2024quatropp Fig. 2, KITTI example; secondary)",[],[],"SAC-IA: select s sample points with pairwise distances above d_min, pick for each a random correspondence among points with similar histograms, compute the rigid transform and score it with a Huber penalty; repeat (1000 iterations in Sec. V) and keep the best transform, then refine with Levenberg-Marquardt non-linear optimization","FPFH(p) = SPFH(p) + (1\u002Fk) sum_i (1\u002Fw_i) SPFH(p_i): each point first gets a Simplified PFH from the three angular features (alpha, phi, theta) of a Darboux uvn frame between the point and its neighbours, then neighbour SPFHs are weighted by distance; the fourth (distance) feature of earlier PFH is dropped and the three features are binned as separate concatenated histograms rather than a 5x5x5 = 125-bin joint histogram; complexity O(n k) vs O(n k^2) for PFH; a multi-radius persistence analysis keeps salient points; SAC-IA matches each sample point to one of the points with similar histograms","not_applicable","none","point clouds with local descriptors","none (coarse alignment into convergence basin)","initial rigid alignment","Table I (Ljubljana outdoor pair, about 45% overlap): SAC-IA 34 s for 1000 iterations using 10462 points (best transform at iteration 476) vs greedy initial alignment > 17 min with 200 points and > 43 min with 250 points; caching with point reordering reduced PFH time on bunny00 (Fig. 4); a 2 GB cache holds feature values of more than 1.3e8 point pairs; online FPFH for single-sweep scans runs close to real time with a small delay (Alg. 1); hardware not reported",null,"not_verified",[],{"id":5,"kind":42,"shortName":7,"title":8,"authors":43,"year":9,"venue":47,"venueType":48,"publisher":49,"volumeIssuePages":50,"doi":51,"arxivId":38,"url":52,"firstPublicDate":53,"publicationStatus":16,"metadataStatus":54,"fulltextStatus":15,"era":10,"classicReason":55,"codeUrl":38,"cluster":11,"topics":56,"mdpi":57,"verification":58,"label":6,"fulltextRoute":59,"versionRead":60,"addedByCensus":57},"component",[44,45,46],"Radu Bogdan Rusu","Nico Blodow","Michael Beetz","2009 IEEE International Conference on Robotics and Automation","conference","IEEE","pp. 3212-3217","10.1109\u002Frobot.2009.5152473","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1109\u002FROBOT.2009.5152473","2009-05","metadata_verified","reproducible baseline: FPFH is the handcrafted descriptor used to generate correspondences in FGR, TEASER++ experiments and improved upon by KISS-Matcher's Faster-PFH.",[11],false,"confirmed","other","author-prepared manuscript (pdfTeX, created 2009-02-03, TUM affiliation header, no IEEE copyright line), 6 pages matching ICRA 2009 pp. 3212-3217; not compared against the IEEE Xplore version of record",[],[],{"totalRows":64,"groupCount":65,"groups":66,"others":726},68,12,[67,313,474,607],{"slug":68,"group":69,"sourceId":70,"sourceLabel":71,"table":72,"selfRows":73,"metrics":74,"seqs":83,"entrants":104,"cells":118,"outcomes":307,"locators":308,"hardware":309,"wordings":310,"notes":311},"sun2025nss-table-5","sun2025nss:Table 5","sun2025nss","Sun et al., 2025","Table 5",18,[75,79],{"label":76,"unit":77,"statistic":78,"alignment":33},"registration recall (RRE \u003C 10 deg and RTE \u003C 0.2 m)","%","not_reported",{"label":80,"unit":81,"statistic":82,"alignment":33},"RMSE [m] (column in Table 5; definition not given in the evaluation-metrics text)","m","RMSE",[84,88,90,92,94,96,98,100,102],{"dataset":85,"sequence":86,"environment":87},"Nothing Stands Still (NSS)","Cross-Area split, all spatiotemporal pairs","indoor building areas under construction or renovation (NSS areas A-F)",{"dataset":85,"sequence":89,"environment":87},"Cross-Stage split, all spatiotemporal pairs",{"dataset":85,"sequence":91,"environment":87},"Original split, all spatiotemporal pairs",{"dataset":85,"sequence":93,"environment":87},"Cross-Area split, only same-stage pairs",{"dataset":85,"sequence":95,"environment":87},"Cross-Stage split, only same-stage pairs",{"dataset":85,"sequence":97,"environment":87},"Original split, only same-stage pairs",{"dataset":85,"sequence":99,"environment":87},"Cross-Area split, only different-stage pairs",{"dataset":85,"sequence":101,"environment":87},"Cross-Stage split, only different-stage pairs",{"dataset":85,"sequence":103,"environment":87},"Original split, only different-stage pairs",[105,108,111,113,115],{"name":106,"methodId":5,"linkable":107,"proposed":57,"self":107},"FPFH",true,{"name":109,"methodId":110,"linkable":107,"proposed":57,"self":57},"FCGF","choy2019fcgf",{"name":112,"methodId":38,"linkable":57,"proposed":57,"self":57},"D3Feat",{"name":114,"methodId":38,"linkable":57,"proposed":57,"self":57},"Predator",{"name":116,"methodId":117,"linkable":107,"proposed":57,"self":57},"GeoTransformer","qin2023geotransformer",[119,123,126,128,130,133,135,137,139,141,143,145,147,149,151,153,155,157,159,162,164,166,168,170,172,175,177,179,181,183,185,187,189,191,193,196,198,200,202,204,206,208,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,248,250,253,255,258,260,262,264,266,268,270,272,274,276,278,280,282,284,286,288,290,292,294,296,298,299,301,303,305],[120,120,120,121,122,120,122,122,120],0,22.83,-1,[120,124,120,125,122,120,122,122,120],1,3.3,[120,120,124,127,122,120,122,122,120],18.73,[120,124,124,129,122,120,122,122,120],2.53,[120,120,131,132,122,120,122,122,120],2,11.7,[120,124,131,134,122,120,122,122,120],2.52,[124,120,120,136,122,120,122,122,120],28.22,[124,124,120,138,122,120,122,122,120],2.07,[124,120,124,140,122,120,122,122,120],37.7,[124,124,124,142,122,120,122,122,120],1.81,[124,120,131,144,122,120,122,122,120],24.43,[124,124,131,146,122,120,122,122,120],2.24,[131,120,120,148,122,120,122,122,120],31.77,[131,124,120,150,122,120,122,122,120],1.98,[131,120,124,152,122,120,122,122,120],51.37,[131,124,124,154,122,120,122,122,120],1.62,[131,120,131,156,122,120,122,122,120],22.73,[131,124,131,158,122,120,122,122,120],2.37,[160,120,120,161,122,120,122,122,120],3,55.53,[160,124,120,163,122,120,122,122,120],1.09,[160,120,124,165,122,120,122,122,120],76.73,[160,124,124,167,122,120,122,122,120],0.77,[160,120,131,169,122,120,122,122,120],64.97,[160,124,131,171,122,120,122,122,120],0.71,[173,120,120,174,122,120,122,122,120],4,38.13,[173,124,120,176,122,120,122,122,120],1.24,[173,120,124,178,122,120,122,122,120],47.78,[173,124,124,180,122,120,122,122,120],0.98,[173,120,131,182,122,120,122,122,120],39.07,[173,124,131,184,122,120,122,122,120],0.96,[120,120,160,186,122,120,122,122,120],32.86,[120,124,160,188,122,120,122,122,120],2.46,[120,120,173,190,122,120,122,122,120],46.4,[120,124,173,192,122,120,122,122,120],1.94,[120,120,194,195,122,120,122,122,120],5,30.82,[120,124,194,197,122,120,122,122,120],2.58,[124,120,160,199,122,120,122,122,120],39.32,[124,124,160,201,122,120,122,122,120],1.88,[124,120,173,203,122,120,122,122,120],44.65,[124,124,173,205,122,120,122,122,120],1.77,[124,120,194,207,122,120,122,122,120],42.86,[124,124,194,146,122,120,122,122,120],[131,120,160,210,122,120,122,122,120],43.62,[131,124,160,212,122,120,122,122,120],1.91,[131,120,173,214,122,120,122,122,120],58.47,[131,124,173,216,122,120,122,122,120],1.48,[131,120,194,218,122,120,122,122,120],36.51,[131,124,194,220,122,120,122,122,120],2.09,[160,120,160,222,122,120,122,122,120],76.8,[160,124,160,224,122,120,122,122,120],0.81,[160,120,173,226,122,120,122,122,120],87.49,[160,124,173,228,122,120,122,122,120],0.44,[160,120,194,230,122,120,122,122,120],92.99,[160,124,194,232,122,120,122,122,120],0.27,[173,120,160,234,122,120,122,122,120],50.88,[173,124,160,236,122,120,122,122,120],1.07,[173,120,173,238,122,120,122,122,120],54.07,[173,124,173,240,122,120,122,122,120],0.79,[173,120,194,242,122,120,122,122,120],55.59,[173,124,194,244,122,120,122,122,120],0.69,[120,120,246,247,122,120,122,122,120],6,1.06,[120,124,246,249,122,120,122,122,120],4.88,[120,120,251,252,122,120,122,122,120],7,0.82,[120,124,251,254,122,120,122,122,120],4.23,[120,120,256,257,122,120,122,122,120],8,0.42,[120,124,256,259,122,120,122,122,120],4.21,[124,120,246,261,122,120,122,122,120],5.21,[124,124,246,263,122,120,122,122,120],3.22,[124,120,251,265,122,120,122,122,120],14.06,[124,124,251,267,122,120,122,122,120],4.15,[124,120,256,269,122,120,122,122,120],10.52,[124,124,256,271,122,120,122,122,120],3.28,[131,120,246,273,122,120,122,122,120],6.12,[131,124,246,275,122,120,122,122,120],2.01,[131,120,251,277,122,120,122,122,120],12.85,[131,124,251,279,122,120,122,122,120],2.4,[131,120,256,281,122,120,122,122,120],4.76,[131,124,256,283,122,120,122,122,120],2.75,[160,120,246,285,122,120,122,122,120],9.49,[160,124,246,287,122,120,122,122,120],1.71,[160,120,251,289,122,120,122,122,120],18.42,[160,124,251,291,122,120,122,122,120],2.03,[160,120,256,293,122,120,122,122,120],28.42,[160,124,256,295,122,120,122,122,120],1.28,[173,120,246,297,122,120,122,122,120],10.55,[173,124,246,154,122,120,122,122,120],[173,120,251,300,122,120,122,122,120],13.39,[173,124,251,302,122,120,122,122,120],2.25,[173,120,256,304,122,120,122,122,120],17.51,[173,124,256,306,122,120,122,122,120],1.31,[],[72],[],[],[312],"Pairwise spatiotemporal registration on NSS; success = RRE \u003C 10 deg and RTE \u003C 0.2 m; methods retrained per split following original protocols. TE and RE columns (successful pairs \u002F all pairs) not transcribed.",{"slug":314,"group":315,"sourceId":316,"sourceLabel":317,"table":318,"selfRows":319,"metrics":320,"seqs":331,"entrants":348,"cells":358,"outcomes":468,"locators":469,"hardware":470,"wordings":471,"notes":472},"lamp2-2022-table-ii","lamp2_2022:Table II","lamp2_2022","Chang et al., 2022","Table II",16,[321,323,325,328],{"label":322,"unit":77,"statistic":78,"alignment":32},"recall of correct loop closures passing SAC and ICP",{"label":324,"unit":77,"statistic":78,"alignment":32},"false-positive rate of false loop closures passing SAC and ICP",{"label":326,"unit":81,"statistic":327,"alignment":32},"mean translation error of accepted correct loop closures","mean",{"label":329,"unit":330,"statistic":327,"alignment":32},"mean rotation error of accepted correct loop closures","deg",[332,336,340,344],{"dataset":333,"sequence":334,"environment":335},"CoSTAR multi-robot dataset: Tunnel","Tunnel","NIOSH Safety Research Coal Mine, Pittsburgh (narrow, mostly featureless tunnels)",{"dataset":337,"sequence":338,"environment":339},"CoSTAR multi-robot dataset: Urban","Urban","Satsop abandoned nuclear power plant, Elma (two floors, open areas, small rooms, stairs)",{"dataset":341,"sequence":342,"environment":343},"CoSTAR multi-robot dataset: Final","Final","DARPA SubT Finals course, Louisville Mega Cavern (tunnel, cave and urban-like)",{"dataset":345,"sequence":346,"environment":347},"CoSTAR multi-robot dataset: KU","KU","Kentucky Underground Storage limestone mine, Wilmore (10-20 m wide tunnels)",[349,351,353,356],{"name":350,"methodId":38,"linkable":57,"proposed":57,"self":57},"GT initialization (oracle)",{"name":352,"methodId":38,"linkable":57,"proposed":57,"self":57},"OdomRot [8] initialization (LAMP 1.0)",{"name":354,"methodId":355,"linkable":107,"proposed":107,"self":57},"TEASER++ initialization + GICP","yang2021teaser",{"name":357,"methodId":5,"linkable":107,"proposed":107,"self":107},"SAC-IA initialization + GICP",[359,361,363,365,367,369,371,372,374,376,378,380,382,384,386,388,390,391,392,394,396,398,400,402,403,404,406,407,408,410,411,413,414,416,418,419,421,422,424,426,428,430,432,434,435,437,438,440,441,442,444,446,448,450,451,453,454,456,458,460,462,463,465,467],[120,120,120,360,122,120,122,122,120],90.8,[124,120,120,362,122,120,122,122,120],93.9,[131,120,120,364,122,120,122,122,120],76.6,[160,120,120,366,122,120,122,122,120],81.9,[120,120,124,368,122,120,122,122,120],90.5,[124,120,124,370,122,120,122,122,120],78.2,[131,120,124,370,122,120,122,122,120],[160,120,124,373,122,120,122,122,120],79.6,[120,120,131,375,122,120,122,122,120],89.2,[124,120,131,377,122,120,122,122,120],83.4,[131,120,131,379,122,120,122,122,120],68.4,[160,120,131,381,122,120,122,122,120],57,[120,120,160,383,122,120,122,122,120],29,[124,120,160,385,122,120,122,122,120],11.3,[131,120,160,387,122,120,122,122,120],18.5,[160,120,160,389,122,120,122,122,120],17.7,[120,124,120,131,122,120,122,122,120],[124,124,120,279,122,120,122,122,120],[131,124,120,393,122,120,122,122,120],1.2,[160,124,120,395,122,120,122,122,120],1.4,[120,124,124,397,122,120,122,122,120],0.8,[124,124,124,399,122,120,122,122,120],1.6,[131,124,124,401,122,120,122,122,120],0.6,[160,124,124,124,122,120,122,122,120],[120,124,131,393,122,120,122,122,120],[124,124,131,405,122,120,122,122,120],7.4,[131,124,131,401,122,120,122,122,120],[160,124,131,124,122,120,122,122,120],[120,124,160,409,122,120,122,122,120],0.4,[124,124,160,120,122,120,122,122,120],[131,124,160,412,122,120,122,122,120],0.2,[160,124,160,120,122,120,122,122,120],[120,131,120,415,122,120,122,122,120],0.09,[124,131,120,417,122,120,122,122,120],0.86,[131,131,120,171,122,120,122,122,120],[160,131,120,420,122,120,122,122,120],0.67,[120,131,124,228,122,120,122,122,120],[124,131,124,423,122,120,122,122,120],1.89,[131,131,124,425,122,120,122,122,120],0.38,[160,131,124,427,122,120,122,122,120],0.52,[120,131,131,429,122,120,122,122,120],0.06,[124,131,131,431,122,120,122,122,120],1.65,[131,131,131,433,122,120,122,122,120],0.32,[160,131,131,401,122,120,122,122,120],[120,131,160,436,122,120,122,122,120],0.26,[124,131,160,252,122,120,122,122,120],[131,131,160,439,122,120,122,122,120],0.29,[160,131,160,439,122,120,122,122,120],[120,160,120,417,122,120,122,122,120],[124,160,120,443,122,120,122,122,120],8.02,[131,160,120,445,122,120,122,122,120],10.82,[160,160,120,447,122,120,122,122,120],9.63,[120,160,124,449,122,120,122,122,120],1.47,[124,160,124,150,122,120,122,122,120],[131,160,124,452,122,120,122,122,120],1.36,[160,160,124,399,122,120,122,122,120],[120,160,131,455,122,120,122,122,120],1.11,[124,160,131,457,122,120,122,122,120],6.43,[131,160,131,459,122,120,122,122,120],2.39,[160,160,131,461,122,120,122,122,120],2.99,[120,160,160,184,122,120,122,122,120],[124,160,160,464,122,120,122,122,120],1.34,[131,160,160,466,122,120,122,122,120],1.45,[160,160,160,216,122,120,122,122,120],[],[318],[],[],[473],"Loop-closure relative pose estimation with different ICP initializations on ground-truth and false loop-closure sets; SAC cumulative error threshold 32 m (500 iterations), ICP threshold 0.9 m (200 iterations); errors computed on correct loop closures that passed SAC and ICP",{"slug":475,"group":476,"sourceId":110,"sourceLabel":477,"table":72,"selfRows":478,"metrics":479,"seqs":483,"entrants":504,"cells":517,"outcomes":601,"locators":602,"hardware":603,"wordings":604,"notes":605},"choy2019fcgf-table-5","choy2019fcgf:Table 5","Choy et al., 2019",9,[480],{"label":481,"unit":482,"statistic":78,"alignment":33},"registration recall","fraction",[484,488,490,492,494,496,498,500,502],{"dataset":485,"sequence":486,"environment":487},"3DMatch registration set","Kitchen","indoor",{"dataset":485,"sequence":489,"environment":487},"Home 1",{"dataset":485,"sequence":491,"environment":487},"Home 2",{"dataset":485,"sequence":493,"environment":487},"Hotel 1",{"dataset":485,"sequence":495,"environment":487},"Hotel 2",{"dataset":485,"sequence":497,"environment":487},"Hotel 3",{"dataset":485,"sequence":499,"environment":487},"Study",{"dataset":485,"sequence":501,"environment":487},"Lab",{"dataset":485,"sequence":503,"environment":487},"Average",[505,507,509,511,513,515],{"name":506,"methodId":5,"linkable":107,"proposed":57,"self":107},"FPFH [23]",{"name":508,"methodId":38,"linkable":57,"proposed":57,"self":57},"USC [29]",{"name":510,"methodId":38,"linkable":57,"proposed":57,"self":57},"CGF [17]",{"name":512,"methodId":38,"linkable":57,"proposed":57,"self":57},"3DMatch [36]",{"name":514,"methodId":38,"linkable":57,"proposed":57,"self":57},"PPFNet [7]",{"name":516,"methodId":110,"linkable":107,"proposed":107,"self":57},"Ours (FCGF)",[518,520,522,524,525,526,528,530,531,532,533,535,537,539,540,541,543,545,546,548,549,550,552,553,555,557,558,559,561,563,564,565,567,569,571,573,574,576,577,579,581,583,585,586,588,589,591,593,594,595,597,598,599,600],[120,120,120,519,122,120,122,122,120],0.36,[120,120,124,521,122,120,122,122,120],0.56,[120,120,131,523,122,120,122,122,120],0.43,[120,120,160,439,122,120,122,122,120],[120,120,173,519,122,120,122,122,120],[120,120,194,527,122,120,122,122,120],0.61,[120,120,246,529,122,120,122,122,120],0.31,[120,120,251,529,122,120,122,122,120],[120,120,256,409,122,120,122,122,120],[124,120,120,427,122,120,122,122,120],[124,120,124,534,122,120,122,122,120],0.35,[124,120,131,536,122,120,122,122,120],0.47,[124,120,160,538,122,120,122,122,120],0.53,[124,120,173,412,122,120,122,122,120],[124,120,194,425,122,120,122,122,120],[124,120,246,542,122,120,122,122,120],0.46,[124,120,251,544,122,120,122,122,120],0.49,[124,120,256,523,122,120,122,122,120],[131,120,120,547,122,120,122,122,120],0.72,[131,120,124,244,122,120,122,122,120],[131,120,131,542,122,120,122,122,120],[131,120,160,551,122,120,122,122,120],0.55,[131,120,173,544,122,120,122,122,120],[131,120,194,554,122,120,122,122,120],0.65,[131,120,246,556,122,120,122,122,120],0.48,[131,120,251,257,122,120,122,122,120],[131,120,256,521,122,120,122,122,120],[160,120,120,560,122,120,122,122,120],0.85,[160,120,124,562,122,120,122,122,120],0.78,[160,120,131,527,122,120,122,122,120],[160,120,160,240,122,120,122,122,120],[160,120,173,566,122,120,122,122,120],0.59,[160,120,194,568,122,120,122,122,120],0.58,[160,120,246,570,122,120,122,122,120],0.63,[160,120,251,572,122,120,122,122,120],0.51,[160,120,256,420,122,120,122,122,120],[173,120,120,575,122,120,122,122,120],0.9,[173,120,124,568,122,120,122,122,120],[173,120,131,578,122,120,122,122,120],0.57,[173,120,160,580,122,120,122,122,120],0.75,[173,120,173,582,122,120,122,122,120],0.68,[173,120,194,584,122,120,122,122,120],0.88,[173,120,246,582,122,120,122,122,120],[173,120,251,587,122,120,122,122,120],0.62,[173,120,256,171,122,120,122,122,120],[194,120,120,590,122,120,122,122,120],0.93,[194,120,124,592,122,120,122,122,120],0.91,[194,120,131,171,122,120,122,122,120],[194,120,160,592,122,120,122,122,120],[194,120,173,596,122,120,122,122,120],0.87,[194,120,194,244,122,120,122,122,120],[194,120,246,580,122,120,122,122,120],[194,120,251,397,122,120,122,122,120],[194,120,256,252,122,120,122,122,120],[],[72],[],[],[606],"Registration recall on the 3DMatch registration set; RANSAC with early termination; pair correct if overlap >= 30% and RMSE \u003C 0.2 m",{"slug":608,"group":609,"sourceId":610,"sourceLabel":611,"table":612,"selfRows":246,"metrics":613,"seqs":620,"entrants":629,"cells":645,"outcomes":720,"locators":721,"hardware":722,"wordings":723,"notes":724},"zhou2016fgr-table-1","zhou2016fgr:Table 1","zhou2016fgr","Zhou et al., 2016","Table 1",[614,617],{"label":615,"unit":616,"statistic":327,"alignment":33},"Average RMSE","surface diameter",{"label":618,"unit":616,"statistic":619,"alignment":33},"Maximal RMSE","max",[621,625,627],{"dataset":622,"sequence":623,"environment":624},"Synthetic range images (AIM@SHAPE, Berkeley Angel, Stanford Bunny)","sigma 0","synthetic",{"dataset":622,"sequence":626,"environment":624},"sigma 0.0025",{"dataset":622,"sequence":628,"environment":624},"sigma 0.005",[630,633,635,637,639,641,643],{"name":631,"methodId":632,"linkable":107,"proposed":57,"self":57},"GoICP [42]","yang2016goicp",{"name":634,"methodId":632,"linkable":107,"proposed":57,"self":57},"GoICP-Trimming [42]",{"name":636,"methodId":38,"linkable":57,"proposed":57,"self":57},"Super 4PCS [26]",{"name":638,"methodId":38,"linkable":57,"proposed":57,"self":57},"OpenCV [8] (implementation of Drost et al.)",{"name":640,"methodId":5,"linkable":107,"proposed":57,"self":107},"PCL [19,34] (PCL implementation of Rusu et al.)",{"name":642,"methodId":38,"linkable":57,"proposed":57,"self":57},"CZK [7] (Choi et al. variant of Rusu's algorithm)",{"name":644,"methodId":610,"linkable":107,"proposed":107,"self":57},"Our approach (FGR)",[646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,677,679,681,683,685,687,689,690,692,694,696,697,699,701,703,704,705,707,709,710,712,713,714,716,718,719],[120,120,120,647,122,120,122,122,120],0.029,[120,124,120,649,122,120,122,122,120],0.13,[120,120,124,651,122,120,122,122,120],0.032,[120,124,124,653,122,120,122,122,120],0.133,[120,120,131,655,122,120,122,122,120],0.037,[120,124,131,657,122,120,122,122,120],0.127,[124,120,120,659,122,120,122,122,120],0.035,[124,124,120,661,122,120,122,122,120],0.473,[124,120,124,663,122,120,122,122,120],0.039,[124,124,124,665,122,120,122,122,120],0.475,[124,120,131,667,122,120,122,122,120],0.044,[124,124,131,669,122,120,122,122,120],0.478,[131,120,120,671,122,120,122,122,120],0.012,[131,124,120,673,122,120,122,122,120],0.019,[131,120,124,675,122,120,122,122,120],0.014,[131,124,124,647,122,120,122,122,120],[131,120,131,678,122,120,122,122,120],0.017,[131,124,131,680,122,120,122,122,120],0.095,[160,120,120,682,122,120,122,122,120],0.009,[160,124,120,684,122,120,122,122,120],0.013,[160,120,124,686,122,120,122,122,120],0.018,[160,124,124,688,122,120,122,122,120],0.212,[160,120,131,651,122,120,122,122,120],[160,124,131,691,122,120,122,122,120],0.242,[173,120,120,693,122,120,122,122,120],0.003,[173,124,120,695,122,120,122,122,120],0.005,[173,120,124,682,122,120,122,122,120],[173,124,124,698,122,120,122,122,120],0.061,[173,120,131,700,122,120,122,122,120],0.111,[173,124,131,702,122,120,122,122,120],0.414,[194,120,120,693,122,120,122,122,120],[194,124,120,695,122,120,122,122,120],[194,120,124,706,122,120,122,122,120],0.008,[194,124,124,708,122,120,122,122,120],0.022,[194,120,131,659,122,120,122,122,120],[194,124,131,711,122,120,122,122,120],0.274,[246,120,120,693,122,120,122,122,120],[246,124,120,695,122,120,122,122,120],[246,120,124,715,122,120,122,122,120],0.006,[246,124,124,717,122,120,122,122,120],0.011,[246,120,131,706,122,120,122,122,120],[246,124,131,678,122,120,122,122,120],[],[612],[],[],[725],"25 synthetic range-image pairs per noise level; RMSE of ground-truth correspondence distances, unit surface diameter; GoICP variants on 1,000 points",[727,733,739,745,750,758,765,771],{"group":728,"slug":729,"sourceLabel":611,"table":730,"selfRows":246,"datasets":731},"zhou2016fgr:Table 2","zhou2016fgr-table-2","Table 2",[732],"Synthetic range images",{"group":734,"slug":735,"sourceLabel":477,"table":612,"selfRows":160,"datasets":736},"choy2019fcgf:Table 1","choy2019fcgf-table-1",[737,738],"3DMatch","3DMatch with rotation augmentation",{"group":740,"slug":741,"sourceLabel":6,"table":742,"selfRows":160,"datasets":743},"rusu2009fpfh:Table I","rusu2009fpfh-table-i","Table I",[744],"Ljubljana outdoor dataset (from ref. [2])",{"group":746,"slug":747,"sourceLabel":611,"table":72,"selfRows":160,"datasets":748},"zhou2016fgr:Table 5","zhou2016fgr-table-5",[749],"Choi et al. scene benchmark",{"group":751,"slug":752,"sourceLabel":753,"table":754,"selfRows":124,"datasets":755},"lim2025kissmatcher:Text Sec. III-C","lim2025kissmatcher-text-sec-iii-c","Lim et al., 2025","Text Sec. III-C",[756,757],"KITTI and MulRan","voxelized 64-channel LiDAR scans (dataset not named in Sec. III-C; KITTI and MulRan are the 64-channel datasets used)",{"group":759,"slug":760,"sourceLabel":761,"table":762,"selfRows":124,"datasets":763},"stoyanov2012d2dndt:Text Sec. 6.1","stoyanov2012d2dndt-text-sec-6-1","Stoyanov et al., 2012","Text Sec. 6.1",[764],"simulated Willow and Terrain data sets (ROS\u002FGazebo)",{"group":766,"slug":767,"sourceLabel":611,"table":768,"selfRows":124,"datasets":769},"zhou2016fgr:Table 4","zhou2016fgr-table-4","Table 4",[770],"UWA benchmark",{"group":772,"slug":773,"sourceLabel":611,"table":774,"selfRows":124,"datasets":775},"zhou2016fgr:Text Sec.5.1","zhou2016fgr-text-sec-5-1","Text Sec.5.1",[770],1790510664999]